dataforge/fn_registry
1
0
Fork 0
Code Issues Pull Requests 5 Actions Packages Projects Releases Wiki Activity

merge(eda): portada v2 (sin Criterios, descripcion LLM, resumen a la derecha) + zebra global PDF + nombre PPTX grande/subrayado

Browse Source
This commit is contained in:
Egutierrez
2026-06-30 22:53:46 +02:00
parent ecc22d6d57 80d10010f5
commit f2eb782a5f
4 changed files with 77 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/functions/datascience/automatic_eda/chapters/portada.py
+11 -14
View File
@@ -26,7 +26,7 @@ from datetime import datetime, timezone
from .. import model
CHAPTER_VERSION = "1.2.0"
CHAPTER_VERSION = "1.3.0"
CHAPTER_ID = "portada"
CHAPTER_TITLE = "Portada"
@@ -35,12 +35,9 @@ CHAPTER_TITLE = "Portada"
# row represents) from it when the LLM layer ran (``run_llm``).
_LLM_KEY = "llm"
# Default human description of what the table quality score measures. Chapters
# can override it via ctx["quality_criteria"].
_DEFAULT_QUALITY_CRITERIA = (
"media de los scores por columna (0–100): completitud (sin nulos/vacíos), "
"validez (tipo y rango coherentes) y consistencia (sin duplicados/constantes)."
)
# Font size (pt) for the dataset name on the PPTX cover slide — notably larger
# than the default H1 so the dataset name stands out (shown underlined too).
_PPTX_TITLE_PT = 44.0
def _storage_from_source(source: str) -> str:
@@ -120,7 +117,8 @@ def _summary_blocks(summary) -> list:
blocks = [model.Heading(text="Resumen del análisis", level=2)]
if rows:
blocks.append(model.KVTable(rows=rows))
# Values pinned to the right margin (numbers flush right, label left).
blocks.append(model.KVTable(rows=rows, value_align="right"))
if titles:
bullets = "\n".join(f"- {model._safe_str(t)}" for t in titles)
blocks.append(model.Markdown(
@@ -213,9 +211,7 @@ def _derive_description(profile: dict, ctx: dict) -> str:
score = profile.get("quality_score")
if score is not None:
parts.append(f"Calidad media estimada: {score}/100.")
parts.append(
"Resumen derivado del perfil; active la interpretación LLM (`run_llm`) "
"para una descripción de negocio más rica.")
parts.append("Resumen derivado del perfil.")
return " ".join(parts)
@@ -259,7 +255,6 @@ def build_portada(profile: dict, ctx: dict):
shape = f"{_fmt_int(n_rows)} filas × {_fmt_int(n_cols)} columnas"
score = profile.get("quality_score")
quality_criteria = ctx.get("quality_criteria") or _DEFAULT_QUALITY_CRITERIA
quality_value = "—" if score is None else f"{score} / 100"
llm = _llm_block(profile, ctx)
@@ -282,8 +277,11 @@ def build_portada(profile: dict, ctx: dict):
# Title + dataset size shown together and BIG (Heading) at the top, kept on
# the same page (Group). The size is no longer buried in the metadata table.
# The dataset name is shown big and underlined on the PPTX cover slide
# (size_pt/underline are honoured by the PPTX renderer; the PDF ignores them).
cover = [
model.Heading(text=str(dataset_name), level=1),
model.Heading(text=str(dataset_name), level=1, underline=True,
size_pt=_PPTX_TITLE_PT),
model.Markdown(text="**Automatic-EDA** · informe exploratorio automático"),
model.Heading(text=shape, level=2),
]
@@ -295,7 +293,6 @@ def build_portada(profile: dict, ctx: dict):
("Almacenamiento", storage),
("Generado", when),
("Calidad", quality_value),
("Criterios de calidad", quality_criteria),
]),
model.Heading(text="Descripción", level=2),
model.Markdown(text=str(description)),
python/functions/datascience/automatic_eda/model.py
+26 -4
View File
@@ -38,10 +38,18 @@ ENGINE_NAME = "AutomaticEDA"
# --------------------------------------------------------------------------- #
@dataclass
class Heading:
"""A section heading. ``level`` 1 (largest) .. 3 (smallest)."""
"""A section heading. ``level`` 1 (largest) .. 3 (smallest).
``underline`` and ``size_pt`` are optional emphasis hints honoured by the
PPTX renderer (the cover uses them to show the dataset name big and
underlined). ``size_pt`` overrides the per-level font size when set; the PDF
renderer ignores both so its layout is unchanged.
"""
text: str = ""
level: int = 1
underline: bool = False
size_pt: Optional[float] = None
kind: str = field(default="heading", init=False)
@@ -62,10 +70,17 @@ class Markdown:
@dataclass
class KVTable:
"""A two-column key/value table. ``rows`` is a list of ``(label, value)``."""
"""A two-column key/value table. ``rows`` is a list of ``(label, value)``.
``value_align`` controls the horizontal alignment of the value column in the
PDF renderer: ``"left"`` (default) keeps values next to the label column;
``"right"`` pins them to the right margin (used by the cover's analysis
summary so the numbers line up flush right).
"""
rows: list = field(default_factory=list)
title: Optional[str] = None
value_align: str = "left"
kind: str = field(default="kv_table", init=False)
@@ -210,13 +225,20 @@ def as_block(obj: Any):
# Build only with fields the dataclass accepts (ignore extras).
try:
if cls is Heading:
size_pt = obj.get("size_pt")
return Heading(text=_safe_str(obj.get("text")),
level=int(obj.get("level", 1) or 1))
level=int(obj.get("level", 1) or 1),
underline=bool(obj.get("underline", False)),
size_pt=(float(size_pt)
if isinstance(size_pt, (int, float))
else None))
if cls is Markdown:
return Markdown(text=_safe_str(obj.get("text")))
if cls is KVTable:
return KVTable(rows=list(obj.get("rows") or []),
title=obj.get("title"))
title=obj.get("title"),
value_align=_safe_str(
obj.get("value_align")) or "left")
if cls is DataTable:
return DataTable(header=list(obj.get("header") or []),
rows=list(obj.get("rows") or []),
python/functions/datascience/automatic_eda/render_pdf_impl.py
+26 -4
View File
@@ -317,10 +317,18 @@ def _place_kv_table(st: _PdfState, block) -> None:
if title:
_place_heading(st, model.Heading(title, level=2))
rows = getattr(block, "rows", []) or []
# ``value_align="right"`` pins the value column to the right margin (label
# left, number flush right) — used by the cover's analysis summary.
right = str(getattr(block, "value_align", "left")).lower() == "right"
key_w = 1.9 # inches reserved for the label column.
# Right-aligned values wrap against the full usable width minus the label
# column; left-aligned values wrap against the value column only.
val_chars = tl.chars_per_line(_USABLE_W - key_w - 0.1, _FS_BODY)
lh = tl.line_height_in(_FS_BODY)
for row in rows:
# ``data_idx`` is the 0-based logical row index: even rows (1-based) are
# zebra-shaded → 0-based odd indices, matching the data-table convention so
# every table in the document carries the same striping.
for data_idx, row in enumerate(rows):
try:
label, value = row[0], row[1]
except Exception: # noqa: BLE001
@@ -329,11 +337,25 @@ def _place_kv_table(st: _PdfState, block) -> None:
row_h = lh * len(v_lines) + _ROW_VPAD
_ensure_space(st, row_h)
y0 = st.y
# Faint zebra fill for even rows, drawn first (zorder 0) so striping
# never hides the text/value drawn on top.
if data_idx % 2 == 1:
st.fig.add_artist(Rectangle(
(_xf(_ML), _yf(y0 + row_h)), _xf(_ML + _USABLE_W) - _xf(_ML),
_yf(y0) - _yf(y0 + row_h), transform=st.fig.transFigure,
color=_ZEBRA, lw=0, zorder=0))
st.fig.text(_xf(_ML), _yf(y0), tl.strip_inline_md(model._safe_str(label)),
fontsize=_FS_BODY, color=_MUTED, ha="left", va="top")
fontsize=_FS_BODY, color=_MUTED, ha="left", va="top",
zorder=2)
for k, vl in enumerate(v_lines):
st.fig.text(_xf(_ML + key_w), _yf(y0 + k * lh), vl,
fontsize=_FS_BODY, color=_INK, ha="left", va="top")
if right:
st.fig.text(_xf(_ML + _USABLE_W), _yf(y0 + k * lh), vl,
fontsize=_FS_BODY, color=_INK, ha="right",
va="top", zorder=2)
else:
st.fig.text(_xf(_ML + key_w), _yf(y0 + k * lh), vl,
fontsize=_FS_BODY, color=_INK, ha="left",
va="top", zorder=2)
st.y = y0 + row_h
st.y += _GAP
python/functions/datascience/automatic_eda/render_pptx_impl.py
+14 -4
View File
@@ -135,7 +135,7 @@ def _ensure(st: _PptxState, height: float) -> None:
def _add_text(st: _PptxState, lines: list, fs: float, color, bold=False,
italic=False, indent=0.0, bullet=False) -> None:
italic=False, indent=0.0, bullet=False, underline=False) -> None:
lh = tl.line_height_in(fs)
height = lh * len(lines) + 0.05
_ensure(st, height)
@@ -153,6 +153,7 @@ def _add_text(st: _PptxState, lines: list, fs: float, color, bold=False,
run.font.size = Pt(fs)
run.font.bold = bold
run.font.italic = italic
run.font.underline = underline
run.font.color.rgb = _rgb(color)
st.y += height
@@ -206,10 +207,16 @@ def _add_rich_text(st: _PptxState, rich_lines: list, fs: float, color,
def _place_heading(st: _PptxState, block) -> None:
level = max(1, min(3, int(getattr(block, "level", 1) or 1)))
fs = {1: _FS_H1, 2: _FS_H2, 3: _FS_H3}[level]
# Optional per-heading emphasis (cover dataset name): a larger font and an
# underline. ``size_pt`` overrides the per-level size when set.
size_override = getattr(block, "size_pt", None)
if isinstance(size_override, (int, float)) and size_override > 0:
fs = float(size_override)
underline = bool(getattr(block, "underline", False))
text = tl.strip_inline_md(getattr(block, "text", ""))
st.last_heading = text or st.last_heading
lines = tl.wrap(text, tl.chars_per_line(_USABLE_W, fs))
_add_text(st, lines, fs, _INK, bold=True)
_add_text(st, lines, fs, _INK, bold=True, underline=underline)
st.y += 0.04
@@ -552,9 +559,11 @@ def _place_note(st: _PptxState, block) -> None:
# WITHOUT drawing it so a Group can move whole to the next slide before drawing.
# Over-estimating only triggers an earlier slide break, never a content cut.
# --------------------------------------------------------------------------- #
def _measure_heading_text(text: str, level: int) -> float:
def _measure_heading_text(text: str, level: int, size_pt=None) -> float:
level = max(1, min(3, int(level or 1)))
fs = {1: _FS_H1, 2: _FS_H2, 3: _FS_H3}[level]
if isinstance(size_pt, (int, float)) and size_pt > 0:
fs = float(size_pt)
lines = tl.wrap(tl.strip_inline_md(text), tl.chars_per_line(_USABLE_W, fs))
return tl.line_height_in(fs) * len(lines) + 0.05 + 0.04
@@ -679,7 +688,8 @@ def _measure_block(st: _PptxState, block) -> float:
try:
if kind == "heading":
return _measure_heading_text(getattr(block, "text", ""),
getattr(block, "level", 1))
getattr(block, "level", 1),
size_pt=getattr(block, "size_pt", None))
if kind == "markdown":
return _measure_markdown(block)
if kind in ("figure", "image"):